AI-Assisted Detection for Early Screening of Acute Myeloid Leukemia Using Infrared Spectra and Clinical Biochemical Reports of Blood

Abstract

Early detection and accurate diagnosis of leukemia pose significant challenges due to the disease's complexity and the need for minimally invasive methods. Acute myeloid leukemia (AML) accounts for most cases of adult leukemia, and our goal is to screen out some AML from adults. In this work, we introduce an AI-enhanced system designed to facilitate early screening and diagnosis of AML among adults. Our approach combines the infrared absorption spectra of serum measured with attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR), which identifies distinctive molecular signatures in lyophilized serum, together with standard clinical blood biochemical test results. We developed a multi-modality spectral transformer network (MSTNetwork) to generate latent space feature vectors from these datasets. Subsequently, these vectors were assessed using a linear discriminant analysis (LDA) algorithm to estimate the likelihood of acute myeloid leukemia. By analyzing blood samples from leukemia patients and the negative control (including non-leukemia patients and healthy individuals), we achieved rapid and accurate prediction and identification of acute myeloid leukemia among adults. Compared to conventional methods relying solely on either FTIR spectra or biochemical indicators of blood, our multi-modality classification system demonstrated higher accuracy and sensitivity, ultimately achieving an accuracy of 98% and a sensitivity of 98%, improving the sensitivity by 12% (compared with using only biochemical indicators) or over 6% (compared with using only FTIR spectra). Our multi-modality classification system is also very robust as it gave much smaller standard deviations of the accuracy and sensitivity. Beyond improving early detection, this work also contributes to a more sustainable and intelligent healthcare sector.

Keywords: acute myeloid leukemia; artificial intelligence; blood analysis; early screening; infrared spectroscopy.

Figure 1

Feature value distribution of biochemical indicator data for tumor, normal, and other patients.

Figure 2

Comparison of infrared spectra of lyophilized and non-lyophilized samples.

Figure 3

FTIR curves for positive and negative cases. The blue solid line and red solid line represent the mean values of infrared spectrum curves for positive and negative samples, respectively; the blue range and the red range show the standard deviations of the infrared spectrums for positive and negative samples, respectively.

Figure 4

The structure of multi-modality spectral transformer network (MSTNetwork).

Figure 5

(a) Distribution of the training set after MSTNetwork encoding; (b) Distribution of the validation set after MSTNetwork encoding; (c) Distribution of the test set after MSTNetwork encoding; (d) Distribution of the original training data; (e) Distribution of the original validation data; (f) Distribution of the original test data.

Figure 6

The accuracy corresponding to different batch sizes.

Figure 7

The results of the datasets containing acute myeloid leukemia patients and the control group (including healthy individuals and other patients): (a) Confusion matrix using only biochemical data; (b) Confusion matrix using only the infrared spectroscopy data; (c) Confusion matrix using both infrared spectroscopy and biochemical data.

Figure 8

The results of the datasets containing acute myeloid leukemia patients and the control group (only healthy individuals): (a) Confusion matrix using only biochemical data; (b) Confusion matrix using only the infrared spectroscopy data; (c) Confusion matrix using both infrared spectroscopy and biochemical data.